Looking for Validity or Testing It? The Perils of Stepwise Regression, Extreme-Scores Analysis, Heteroscedasticity, and Measurement Error

When researchers introduce a new test they have to demonstrate that it is valid, using unbiased designs and suitable statistical procedures. In this article we use Monte Carlo analyses to highlight how incorrect statistical procedures (i.e., stepwise regression, extreme scores analyses) or ignoring regression assumptions (e.g., heteroscedasticity) contribute to wrong validity estimates. Beyond these demonstrations, and as an example, we re-examined the results reported by Warwick, Nettelbeck, and Ward (2010) concerning the validity of the Ability Emotional Intelligence Measure (AEIM). Warwick et al. used the wrong statistical procedures to conclude that the AEIM was incrementally valid beyond intelligence and personality traits in predicting various outcomes. In our re-analysis, we found that the reliability-corrected multiple correlation of their measures with personality and intelligence was up to .69. Using robust statistical procedures and appropriate controls, we also found that the AEIM did not predict incremental variance in GPA, stress, loneliness, or well-being, demonstrating the importance for testing validity instead of looking for it.

Stepwise evaluation of unexplained syncope in a large ambulatory population

La syncope est un symptôme clinique fréquent mais son origine demeure indéterminée jusque dans 60% des cas de patients admis dans un centre d'urgences. Le développement de consultations spécialisées de la syncope a considérablement modifié l'évaluation des patients avec une syncope inexpliquée en les orientant vers des stratégies d'investigations non-invasives, tels que le tilt-test, le massage du sinus carotidien et le test ^hyperventilation. Cependant, il existe peu de données dans 10 la littérature concernant dans la performance diagnostique réelle de ces tests fonctionnels.Notre travail de recherche porte sur l'analyse des données des 939 premiers patients adressés à la consultation ambulatoire de la syncope du CHUV pour l'investigation d'une syncope d'origine indéterminée. L'objectif de notre travail de thèse est 1) d'évaluer la performance diagnostique de l'algorithme de prise en charge standardisé et de ses différents tests pratiqués dans le cadre de notre 15 consultation et 2) de déterminer les caractéristiques cliniques communes des patients avec un diagnostic final de syncope d'origine rythmique ou vaso-vagale.Notre travail de thèse démontre qu'un algorithme de prise en charge standardisé basé sur des tests non-invasifs permet de déterminer 2/3 des causes de syncope initialement d'origine indéterminée. Par ailleurs, notre travail montre que des étiologies bénignes, telles que la syncope d'origine vaso- 20 vagale ou psychogène, représentent la moitié des causes syncopales alors que les arythmies cardiaques demeurent peu fréquentes. Finalement, notre travail démontre que l'absence de symptomatologie prodromique, en particulier chez les patients âgés avec une limitation fonctionnelle ou un allongement de la durée de l'onde Ρ à l'électrocardiogramme, suggère une syncope d'origine rythmique. Ce travail de thèse contribuera à optimaliser notre algorithme de prise 25 en charge standardisée de la syncope d'origine indéterminée et ouvre de nouvelles perspectives de recherche dans le développement de modèles basés sur des facteurs cliniques permettant de prédire les principales causes syncopales.

Statistical properties of population differentiation estimators under stepwise mutation in a finite island model.

Microsatellite loci mutate at an extremely high rate and are generally thought to evolve through a stepwise mutation model. Several differentiation statistics taking into account the particular mutation scheme of the microsatellite have been proposed. The most commonly used is R(ST) which is independent of the mutation rate under a generalized stepwise mutation model. F(ST) and R(ST) are commonly reported in the literature, but often differ widely. Here we compare their statistical performances using individual-based simulations of a finite island model. The simulations were run under different levels of gene flow, mutation rates, population number and sizes. In addition to the per locus statistical properties, we compare two ways of combining R(ST) over loci. Our simulations show that even under a strict stepwise mutation model, no statistic is best overall. All estimators suffer to different extents from large bias and variance. While R(ST) better reflects population differentiation in populations characterized by very low gene-exchange, F(ST) gives better estimates in cases of high levels of gene flow. The number of loci sampled (12, 24, or 96) has only a minor effect on the relative performance of the estimators under study. For all estimators there is a striking effect of the number of samples, with the differentiation estimates showing very odd distributions for two samples.

Country actions to meet UN commitments on non-communicable diseases: a stepwise approach.

Strong leadership from heads of state is needed to meet national commitments to the UN political declaration on non-communicable diseases (NCDs) and to achieve the goal of a 25% reduction in premature NCD mortality by 2025 (the 25 by 25 goal). A simple, phased, national response to the political declaration is suggested, with three key steps: planning, implementation, and accountability. Planning entails mobilisation of a multisectoral response to develop and support the national action plan, and to build human, financial, and regulatory capacity for change. Implementation of a few priority and feasible cost-effective interventions for the prevention and treatment of NCDs will achieve the 25 by 25 goal and will need only few additional financial resources. Accountability incorporates three dimensions: monitoring of progress, reviewing of progress, and appropriate responses to accelerate progress. A national NCD commission or equivalent, which is independent of government, is needed to ensure that all relevant stakeholders are held accountable for the UN commitments to NCDs.

Stepwise emergence of azole, echinocandin and amphotericin B multidrug resistance in vivo in Candida albicans orchestrated by multiple genetic alterations.

OBJECTIVES: The objective of this study was to characterize the underlying molecular mechanisms in consecutive clinical Candida albicans isolates from a single patient displaying stepwise-acquired multidrug resistance. METHODS: Nine clinical isolates (P-1 to P-9) were susceptibility tested by EUCAST EDef 7.2 and Etest. P-4, P-5, P-7, P-8 and P-9 were available for further studies. Relatedness was evaluated by MLST. Additional genes were analysed by sequencing (including FKS1, ERG11, ERG2 and TAC1) and gene expression by quantitative PCR (CDR1, CDR2 and ERG11). UV-spectrophotometry and GC-MS were used for sterol analyses. In vivo virulence was determined in the insect model Galleria mellonella and evaluated by log-rank Mantel-Cox tests. RESULTS: P-1 + P-2 were susceptible, P-3 + P-4 fluconazole resistant, P-5 pan-azole resistant, P-6 + P-7 pan-azole and echinocandin resistant and P-8 + P-9 MDR. MLST supported genetic relatedness among clinical isolates. P-4 harboured four changes in Erg11 (E266D, G307S, G450E and V488I), increased expression of ERG11 and CDR2 and a change in Tac1 (R688Q). P-5, P-7, P-8 and P-9 had an additional change in Erg11 (A61E), increased expression of CDR1, CDR2 and ERG11 (except for P-7) and a different amino acid change in Tac1 (R673L). Echinocandin-resistant isolates harboured the Fks1 S645P alteration. Polyene-resistant P-8 + P-9 lacked ergosterol and harboured a frameshift mutation in ERG2 (F105SfsX23). Virulence was attenuated (but equivalent) in the clinical isolates, but higher than in the azole- and echinocandin-resistant unrelated control strain. CONCLUSIONS: C. albicans demonstrates a diverse capacity to adapt to antifungal exposure. Potentially novel resistance-inducing mutations in TAC1, ERG11 and ERG2 require independent validation.

Scaling up stepwise feature introduction to construction of large software systems

Developing software is a difficult and error-prone activity. Furthermore, the complexity of modern computer applications is significant. Hence,an organised approach to software construction is crucial. Stepwise Feature Introduction – created by R.-J. Back – is a development paradigm, in which software is constructed by adding functionality in small increments. The resulting code has an organised, layered structure and can be easily reused. Moreover, the interaction with the users of the software and the correctness concerns are essential elements of the development process, contributing to high quality and functionality of the final product. The paradigm of Stepwise Feature Introduction has been successfully applied in an academic environment, to a number of small-scale developments. The thesis examines the paradigm and its suitability to construction of large and complex software systems by focusing on the development of two software systems of significant complexity. Throughout the thesis we propose a number of improvements and modifications that should be applied to the paradigm when developing or reengineering large and complex software systems. The discussion in the thesis covers various aspects of software development that relate to Stepwise Feature Introduction. More specifically, we evaluate the paradigm based on the common practices of object-oriented programming and design and agile development methodologies. We also outline the strategy to testing systems built with the paradigm of Stepwise Feature Introduction.

Remodeling in the ischemic heart: the stepwise progression for heart

Abstract Coronary artery disease is the leading cause of death in the developed world and in developing countries. Acute mortality from acute myocardial infarction (MI) has decreased in the last decades. However, the incidence of heart failure (HF) in patients with healed infarcted areas is increasing. Therefore, HF prevention is a major challenge to the health system in order to reduce healthcare costs and to provide a better quality of life. Animal models of ischemia and infarction have been essential in providing precise information regarding cardiac remodeling. Several of these changes are maladaptive, and they progressively lead to ventricular dilatation and predispose to the development of arrhythmias, HF and death. These events depend on cell death due to necrosis and apoptosis and on activation of the inflammatory response soon after MI. Systemic and local neurohumoral activation has also been associated with maladaptive cardiac remodeling, predisposing to HF. In this review, we provide a timely description of the cardiovascular alterations that occur after MI at the cellular, neurohumoral and electrical level and discuss the repercussions of these alterations on electrical, mechanical and structural dysfunction of the heart. We also identify several areas where insufficient knowledge limits the adoption of better strategies to prevent HF development in chronically infarcted individuals.

The 21-dehydroxylation of corticosteroids: evidence for an enol intermediate and the hydroxylation of steroids by fungal cyto-chrome P450: evidence for a stepwise mechanism

Two enzyme mechanisms were examined: the 21-dehydroxylation of corticosteroids by the anaerobe Eubacterium l en tum, and the hydroxylation of steroids by fungal cytochrome P450. Deuterium labelling techniques were used to study the enzymic dehydroxylation. Corticosteroids doubly labelled (2H) at the C-21 position were incubated with a culture of Eubacterium lentum. It was found that t he enzymic dehydroxylation proceeded with the loss of one 2H f rom C-21 per molecule of substrate. The kinetic isotope ef fect f or the reaction was found to be k~kD = 2. 28. These results suggest that enzyme/substr ate binding in this case may proceed via t he enol form of the substrate. Also , it appears that this binding is, at least in part, the rate determining step of t he reaction. The hydroxylation of steroids by fungal cytochrome P450 was examined by means of a product study. Steroids with a double bond at the A8 (9), ~( lO ), or ~ (ll) position were synthesized. These steroids were then incubated with fungal strains known to use a cytochrome P450 monooxygenase to hydroxylate at positions allylic to these doubl e bonds. The products formed in these incubations indicated that the double bonds had migrated during allylic hydroxylat ion. This suggests that a carbon centred radical or ion may be an intermediate i n the cytochrome P450 cat alytic cycle.

Stepwise self-assembly of a tripeptide from molecular dimers to supramolecular beta-sheets in crystals and amyloid-like fibrils in the solid state

The terminally protected tripeptide Boc-Ala(1)-Leu(2)-Ala(3)-OMe 1 forms antiparallel hydrogen-bonded dimers of two different conformers in the asymmetric unit and the individual dimers then self-associate to form supramolecular beta-sheet structures in crystals and amyloid-like fibrils in the solid state.

Stepwise construction of [Os6(CO)18(μ6-P)]-, a hexanuclear osmium cluster monoanion with trigonal-prismatic co-ordination for phosphorus: X-ray crystal structures of [Os6(μ-H)2(CO)20(MeCN)(μ3-PH)] and [PPh3Me][Os6(CO)18(μ6-P)]

Treatment of the labile cluster [Os3(CO)11(MeCN)] with PH3 affords the substituted product [Os3(CO)11(PH3)](1) in high yield. Subsequent reaction of (1) with Na2CO3 in MeOH, followed by acidification, gives the hydrido phosphido cluster [Os3(µ-H)(CO)10(µ-PH2)](2). When (2) is heated to 45–60 °C in the presence of [Os3(CO)11(MeCN)] a hexanuclear complex with the formulation [Os6(µ-H)2(CO)21(µ3-PH)](3) is obtained. If this reaction is repeated using [Os3(CO)10(MeCN)2] instead of [Os3(CO)11(MeCN)], an acetonitrile-containing product, [Os6(µ-H)2(CO)20(MeCN)(µ3-PH)](4), is obtained. An X-ray analysis of (4) shows that two Os3 triangular units are linked by a µ3-phosphinidene ligand, which symmetrically bridges an Os–Os edge of one triangle and is terminally co-ordinated to one Os atom of the second triangle. When (3) is treated with a weak base, such as [N(PPh3)2]Cl or [PPh3Me] Br, deprotonation to the corresponding cluster monoanion [Os6(µ-H)(CO)21(µ3-PH)]–(5) occurs. Treatment of (5) with a weak acid regenerates (3) in quantitative yield. Thermolysis of (3) leads to a closing up of the metal framework, affording the cluster [Os6(µ-H)(CO)18(µ6-P)], which readily deprotonates to give the anion [Os6(CO)18(µ6-P)]–(7) in the presence of [N(PPh3)2] Cl or [PPh3Me]Br. The same anion (7) may also be obtained by direct thermolysis of (5). An X-ray analysis of the [PPh3Me]+ salt of (7) confirms that the phosphorus occupies an interstitial site in a trigonal-prismatic hexaosmium framework, and co-ordinates to all six metal atoms with an average Os–P distance of 2.31 (1)Å. Proton and 31P n.m.r. data on all the new clusters are presented, and the position of the phosphorus resonance in the 31P n.m.r. spectrum is related to the changes in the environment of the phosphorus atom.

Implementing stepwise solvent elution in sequential injection chromatography for fluorimetric determination of intracellular free amino acids in the microalgae Tetraselmis gracilis

The concept of sequential injection chromatography (SIC) was exploited to automate the fluorimetric determination of amino acids after pre-column derivatization with ophthaldialdehyde (OPA) in presence of 2-mercaptoethanol (2MCE) using a reverse phase monolithic C(18) stationary phase. The method is low-priced and based on five steps of isocratic elutions. The first step employs the mixture methanol: tetrahydrofuran: 10 mmol L(-1) phosphate buffer (pH 7.2) at the volumetric ratio of 8:1:91; the other steps use methanol: 10 mmol L-1 phosphate buffer (pH 7.2) at volumetric ratios of 20:80, 35:65, SO:SO and 65:35. At a flow rate of 10 mu L s(-1) a 25 mm long-column was able to separate aspartic acid (Asp), glutamic acid (Glu), asparagine (Asn), serine (Ser), glutamine (Gln), glycine (Gly), threonine (Thr), citruline (Ctr), arginine (Arg), alanine (Ala), tyrosine (Tyr), phenylalanine (Phe), ornithine (Orn) and lysine (Lys) with resolution >1.2 as well as methionine (Met) and valine (Val) with resolution of 0.6. Under these conditions isoleucine (Ile) and leucine (Leu) co-eluted. The entire cycle of amino acids derivatization, chromatographic separation and column conditioning at the end of separation lasted 25 min. At a flow rate of 40 mu L s(-1) such time was reduced to 10 min at the cost of resolution worsening for the pairs Ctr/Arg and Orn/Lys. The detection limits varied from 0.092 mu mol L(-1) for Tyr to 0.51 mu mol L(-1) for Orn. The method was successfully applied to the determination of intracellular free amino acids in the green alga Tetraselmis gracilis during a period of seven days of cultivation. Samples spiked with known amounts of amino acids resulted in recoveries between 94 and 112%. (C) 2008 Elsevier B.V. All rights reserved.

Previsão de demanda de cargas elétricas por seleção de variáveis stepwise e redes neurais artificiais

Pós-graduação em Engenharia Elétrica - FEIS